]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mailru.py
Merge tag 'upstream/2014.07.11'
[youtubedl] / youtube_dl / extractor / mailru.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7
8
9 class MailRuIE(InfoExtractor):
10 IE_NAME = 'mailru'
11 IE_DESC = 'Видео@Mail.Ru'
12 _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
13
14 _TESTS = [
15 {
16 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
17 'md5': 'dea205f03120046894db4ebb6159879a',
18 'info_dict': {
19 'id': '46301138',
20 'ext': 'mp4',
21 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
22 'timestamp': 1393232740,
23 'upload_date': '20140224',
24 'uploader': 'sonypicturesrus',
25 'uploader_id': 'sonypicturesrus@mail.ru',
26 'duration': 184,
27 },
28 },
29 {
30 'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
31 'md5': '00a91a58c3402204dcced523777b475f',
32 'info_dict': {
33 'id': '46843144',
34 'ext': 'mp4',
35 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
36 'timestamp': 1397217632,
37 'upload_date': '20140411',
38 'uploader': 'hitech',
39 'uploader_id': 'hitech@corp.mail.ru',
40 'duration': 245,
41 },
42 },
43 ]
44
45 def _real_extract(self, url):
46 mobj = re.match(self._VALID_URL, url)
47 video_id = mobj.group('idv1')
48
49 if not video_id:
50 video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
51
52 video_data = self._download_json(
53 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON')
54
55 author = video_data['author']
56 uploader = author['name']
57 uploader_id = author['id']
58
59 movie = video_data['movie']
60 content_id = str(movie['contentId'])
61 title = movie['title']
62 if title.endswith('.mp4'):
63 title = title[:-4]
64 thumbnail = movie['poster']
65 duration = movie['duration']
66
67 view_count = video_data['views_count']
68
69 formats = [
70 {
71 'url': video['url'],
72 'format_id': video['name'],
73 } for video in video_data['videos']
74 ]
75
76 return {
77 'id': content_id,
78 'title': title,
79 'thumbnail': thumbnail,
80 'timestamp': video_data['timestamp'],
81 'uploader': uploader,
82 'uploader_id': uploader_id,
83 'duration': duration,
84 'view_count': view_count,
85 'formats': formats,
86 }